added link to arXiv paper

CITATION.cff

@@ -0,0 +1,28 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+- family-names: "Cruz"
+  given-names: "André F."
+- family-names: "Hardt"
+  given-names: "Moritz"
+- family-names: "Mendler-Dünner"
+  given-names: "Celestine"
+title: "Evaluating language models as risk scores"
+version: 2.0.4
+doi: 10.48550/arXiv.2407.14614
+date-released: "2024-07-19"
+url: "https://arxiv.org/abs/2407.14614"
+preferred-citation:
+  type: article
+  authors:
+  - family-names: "Cruz"
+    given-names: "André F."
+  - family-names: "Hardt"
+    given-names: "Moritz"
+  - family-names: "Mendler-Dünner"
+    given-names: "Celestine"
+  journal: "arXiv preprint arXiv:2407.14614"
+  doi: 10.48550/arXiv.2407.14614
+  title: "Evaluating language models as risk scores"
+  month: 7
+  year: 2024

README.md

@@ -7,6 +7,8 @@
 ![PyPI - License](https://img.shields.io/pypi/l/folktexts)
 ![Python compatibility](https://badgen.net/pypi/python/folktexts)
 
+> This package is accompanied by a paper titled ["Evaluating language models as risk scores"](https://arxiv.org/abs/2407.14614)
+
 Folktexts is a python package to evaluate statistical properties of LLMs as classifiers.
 It enables computing and evaluating classification _risk scores_ for tabular prediction tasks using LLMs.
 
@@ -23,6 +25,7 @@ Package documentation can be found [here](https://socialfoundations.github.io/fo
 - [Example usage](#example-usage)
 - [Evaluating feature importance](#evaluating-feature-importance)
 - [Benchmark options](#benchmark-options)
+- [Citation](#citation)
 - [License and terms of use](#license-and-terms-of-use)
 
 
@@ -169,6 +172,20 @@ options:
 ```
 
 
+## Citation
+
+```
+@misc{cruz2024evaluating,
+    title={Evaluating language models as risk scores},
+    author={Andr\'{e} F. Cruz and Moritz Hardt and Celestine Mendler-Dünner},
+    year={2024},
+    eprint={2407.14614},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+
 ## License and terms of use
 
 Code licensed under the [MIT license](LICENSE).